© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37516
    Prev
    Next
    INDEX
    Explanations

    references to specific days and significant moments within those days

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    688
    +0.13
    0.6%
    477
    +0.11
    0.5%
    651
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.13
    0.03
    688
    +0.11
    0.02
    132
    +0.11
    0.02
    Negative Logits
    english
    -0.67
     chops
    -0.63
     anecd
    -0.63
    iability
    -0.61
     volunte
    -0.60
    amily
    -0.60
     exha
    -0.58
     behav
    -0.57
     Leban
    -0.57
     regul
    -0.56
    POSITIVE LOGITS
    dream
    0.93
    nings
    0.87
    endment
    0.84
    light
    0.81
     onwards
    0.77
    abouts
    0.76
    terday
    0.76
    scape
    0.75
     onward
    0.75
    glass
    0.74
    Activations Density 0.040%

    No Known Activations